Llama 2 jupyter notebook. ru/0fhwdtw/create-company-profile-online-free.

Project Jupyter builds tools, standards, and services for many different use cases. Jul 31, 2023 · In this video, you'll learn how to use the Llama 2 in Python. With support for interactive conversations, users can easily customize prompts to receive prompt and accurate answers. For example, we will use the Meta-Llama-3-8B-Instruct model for this demo. Download link to a Train the Llama 2 LLM architecture in PyTorch then inference it with one simple 700-line C file . Using its powerful magic commands and chat interface, Jupyter AI Nov 17, 2023 · Use the Mistral 7B model. Jupyter Notebooks are a spin-off project from the IPython project, which used to have an IPython Notebook project itself. pip install notebook. Let’s take a look at an example of this. Contribute to tpaviot/llama. Jupyter Notebook 5. ipynb - Your first (simple) chain. Launching a Jupyter notebook with "Conda" via UI (Control Panel) Jan 10, 2024 · [Bug] "Getting Started with MLC-LLM using the Llama 2 Model" jupyter notebook is not working in colab?! #1571 Closed cosmosanalytics opened this issue Jan 9, 2024 · 5 comments Jupyter notebooks have two different keyboard input modes: In edit mode you can enter code or text in a cell. This is what the generated notebook looks like. This page uses instructions with pip, the recommended installation tool for Python. The llama-recipes repository contains a quick start Jupyter notebook, which can now be run. Information. pth; params. May 22, 2024 · To generate a Jupyter Notebook from a text prompt, start the prompt with the /generate command. Note that I chose Llama 2 because I am able to run it locally on my own machine without racking up all kinds of API fees on OpenAI. I have double checked that whether I run from Jupyter or from the terminal I have the same output for sys. Jul 21, 2023 · Visit the page of one of the LLaMA 2 available models (version 7B, 13B or 70B), and accept Hugging Face’s license terms and acceptable use policy. After installing the application, launch it and click on the “Downloads” button to open the models menu. Jul 28, 2023 · This one package is the only difference between the two lists. Input Models input text only. Before you execute the command, change to the folder where you have placed the notebook before. Go to cmd and write : cd C:\Users\deviv_000\AppData\Roaming\jupyter this will take cmd to that folder. io instance to train Llama-2: Create an account on Runpod. Aug 2, 2023 · Aug 2, 2023. For Windows users, type the following command in Command Prompt: setx HF_TOKEN Apr 20, 2024 · In this article, we will go over how to install Llama 3’s 8B version and run it locally on a jupyter notebook. The 8B model is designed for faster training Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. Command mode binds the keyboard to notebook-level commands and is indicated by a gray cell border with a blue left border. I have also checked that !pip show pip in Jupyter and pip show pip give the same output. 4. Dec 19, 2023 · Llama 2 and prompt engineering; Getting started with prompt engineering using Llama-2-Chat; Prerequisites; Steps; Step 1. 0-py3-none-any. You might think that you need many billion parameter LLMs to do anything useful, but in fact very small LLMs can have surprisingly strong performance if you make the domain narrow enough (ref: TinyStories paper). Launch the new Notebook on Kaggle, and add the Llama 3 model by clicking the + Add Input button, selecting the Models option, and clicking on the plus + button beside the Llama 3 model. Add stream completion. First, we want to load a llama-2-7b-chat-hf model ( chat model) and train it on the mlabonne/guanaco-llama2-1k (1,000 samples), which will produce our fine-tuned model llama-2-7b-miniguanaco. 3, ctransformers, and langchain. Jul 24, 2023 · llama-2-7b/ ├── 7B │ ├── checklist. All 47 Jupyter Notebook 21 Python 19 HTML 2 JavaScript 2 Rust 1 Shell 1 ChatGPT-like chatbot. Use the Panel chat interface to build an AI chatbot with Mistral 7B. path. The official example notebooks/scripts; My own modified scripts; Related Components. 🌎; A notebook on how to run the Llama 2 Chat Model with 4-bit quantization on a local computer or Google Colab. Dec 21, 2019 · First things first, the way you can write down text (non-code) content is to select the cell in a Jupyter Notebook and head over to the dropdown box to select “Markdown”. Atlast after struggling for 3 days i came across this wonderful foolproof solution:-. Llama 2 Jupyter Notebook: This jupyter notebook steps you through how to finetune a Llama 2 model on the text summarization task using the samsum. We encourage you to add your own prompts to the list, and Jul 30, 2023 · 1. Llama 2 is a versatile conversational AI model that can be used effortlessly in both Google Colab and local environments. Running the Notebook. In the search results select Install for the extension. This example uses the meta-llama/Meta-Llama-3-8B model from Hugging Face Hub. 1%; Dockerfile 0. Use our tools without installing anything. cpp-notebook development by creating an account on GitHub. This notebook contains a few extra features to improve formatting of the output as well. - yj90/Master-the-LangChain-Prompt-Engineering-Tutorial This chatbot is created using the open-source Llama 2 LLM model from Meta. Verify the Installation: Write following in terminal. Add new READ token in your Hugging Face settings. bin response time: 71. ipynb and lets get started. ai project; Step 2. ipynb notebook in Jupyter Notebook or Google Colab. Before diving into Colab is a hosted Jupyter Notebook service that requires no setup to use and provides free access to computing resources, including GPUs and TPUs. Included are several Jupyter notebooks that implement sample code found in the Langchain Quickstart guide. Note: We are going to use the Jupyter environment only for preparing the dataset and then torchrun for launching our training script for distributed training. This chatbot is created using the open-source Llama 2 LLM model from Meta. where the Llama 2 model will live on your host machine. *Update*- Running on a Mac M1 (or M2) works quite well. Here is a standalone Jupyter notebook that demonstrates how to ingest information from documents and interact with a large language model to have AI chat answer questions about their content. The notebook uses parameter efficient finetuning (PEFT) and int8 quantization to finetune a 7B on a single GPU like an A10 with 24GB gpu memory. Collecting groq. This tool aims to support all Ollama API endpoints, facilitate model conversion, and ensure seamless connectivity, even in environments behind NAT. Project Jupyter’s tools are available for installation via the Python Package Index, the leading repository of software created for the Python programming language. Log in to the Hugging Face model Hub from your notebook’s terminal by running the huggingface-cli login command, and enter your token. Jan 25, 2024 · Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 4 On-line CPU(s) list: 0-3 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) CPU @ 2. Sep 16, 2023 · I am running a Jupyter notebook for the purpose of running Llama 2 locally in Python. cpp. Aug 1, 2023 · Also refer to the Jupyter Quick Start guide for how to set up Jupyter to be able to run this notebook on a remote IPU machine. whl (75 kB) Aug 9, 2023 · VSCode 1. Instructions. If you’re interested in how this dataset was created, you can check this notebook. If you want to run LLaMA 13B, 33B, 65B models, you can refer to the example. Associate a Watson Machine Learning instance to your project; Step 3: Create and open a Jupyter Notebook or Prompt Lab session; Step 4: Define the prompts; Summary and next steps Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. 28 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr May 3, 2024 · Link to Jupyter Notebook: GitHub page Training LLMs locally on Apple silicon: GitHub page. The code, pretrained models, and fine-tuned Notebooks: Dive into a variety of interactive Jupyter notebooks covering topics such as text generation, fine-tuning, and language understanding using LLMs. Now everything is set up and Jupyter can be started with the following command. A good first step is to open a Jupyter Notebook, type %lsmagic into a cell, and run the cell. saahith May 5, 2024, 5:04pm 1. Use the search function and type ‘Llama2’. Hit Ctrl + Enter to run through the notebook! Jul 18, 2023 · In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters. In the rapidly advancing field of artificial intelligence, the Meta-Llama-3 model stands out for its versatility and robust performance, making it ideally suited for Apple’s innovative silicon architecture. 10. Plus it is definitely smarter than an actual Llama. You can check the time stamps for yourself to verify this. Copy the Model Path from Hugging Face: Head over to the Llama 2 model page on Hugging Face, and copy the model path. Launching a Jupyter notebook with "Conda" via UI (Control Panel) The 7 billion parameter model (LLaMA 2 7B) is 12. May 7, 2024 · How to Use Magics in Jupyter. The notebook consists of a sequence of cells. model_id, trust_remote_code=True, config=model_config, quantization_config=bnb Jul 18, 2023 · A user for AI Notebooks; To access LLaMA 2 models, you will also need to follow the requirements indicated in the notebook. Run the notebook cells sequentially to: Install necessary libraries; Import required modules and classes; Load Neo4j credentials; Set up the OpenAI API key and other settings; Create graph and vector stores; Retrieve documents from Neo4j nodes with text properties Jul 25, 2023 · Let’s talk a bit about the parameters we can tune here. It created a notebook demonstrating a classification use case from scratch in just one minute. Once found, note down the image URL. Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. Get up and running on your computer. I downloaded the 7B parameter Llama 2 model to the root folder of my D: drive. Aug 24, 2023 · Here is how I built a Jupyter notebook (Python) that uses Llama 2 to make this happen locally on my computer. Jupyter AI brings generative artificial intelligence to Jupyter notebooks, giving users the power to explain and generate code, fix errors, summarize content, ask questions about their local files, and generate entire notebooks from a natural language prompt. - Upload pdf or text files for analysis. Create a watsonx. The updated code: model = transformers. chk; consolidated. This is indicated by a green cell border. Build an AI chatbot with both Mistral 7B and Llama2 using LangChain. Add funds within the billing section. Jul 29, 2023 · llama-2-7b-chat. 6GB in size, so it should download fairly quickly. Select deploy for an 8xRTX A6000 instance. Even though I’ve already downloaded them and stored them in the specified cache directory, I’ve been unable to load up the model. Aug 7, 2023 · Here is the link to the Jupyter notebook you need. According to Meta, the release of Llama 3 features pretrained and instruction fine-tuned language models with 8B and 70B parameter counts that can support a broad range of use cases including summarization, classification, information extraction, and content grounded question and answering. Navigate to the Model Tab in the Text Generation WebUI and Download it: Open Oobabooga's Text Generation WebUI in your web browser, and click on the "Model" tab. 2. io. In this section, initialize the Llama-2-70b-chat-hf fine-tuned model with 4-bit and 16-bit precision as described in the following steps. A Jupyter Notebook for fine-tuning a Llama 2 model. In the Export content window, select Registry. Jul 19, 2023 · Llama 2 is a family of open-source large language models released by Meta. 100% private, with no data leaving your device A notebook on how to quantize the Llama 2 model using GPTQ from the AutoGPTQ library. There, you can scroll down and select the “Llama 3 Instruct” model, then click on the “Download” button. For 1–2 example prompts, add relevant static text from external documents as prompt context and assess if the quality of the responses improves. ggmlv3. Our models outperform open-source chat models on most benchmarks we tested, and based on The Llama model is an Open Foundation and Fine-Tuned Chat Models developed by Meta. Then, open your fine-tuning notebook of LangChain & Prompt Engineering tutorials on Large Language Models (LLMs) such as ChatGPT with custom data. Inference Llama 2 in one file of pure Python. Open Colab New Notebook. JupyterLab: A Next-Generation Notebook Interface. - ollama/ollama For this course, I'm going to be using Google Colab, which is a free Jupyter Notebook environment. ipynb - Basic sample, verifies you have valid API key and can call the OpenAI service. You will not need to add your token as git credential. 🤗Transformers. Let's go ahead and launch it by hitting Open Colab. if your downloaded Llama2 model directory resides in your home path, enter /home/[user] Specify the Hugging Face username and API Key secrets. The execution behavior of a cell is determined by the cell’s type. - curiousily/Get-Things-Done-with-Prompt-Engineering-and-LangChain Let's load a meaning representation dataset, and fine-tune Llama 2 on that. The notebook uses parameter efficient finetuning (PEFT) and int8 quantization to finetune a 7B on a single GPU like an A10 with 24GB gpu memory. Introduction. Who can help? @hwchase17 @agol. In this article, I’ll show you some of Oct 9, 2023 · For installing jupyter notebook using pip : Open a Terminal or Command Prompt: Press Ctrl+ALT+T for ubuntu and for windows press ” Windows key +X” to open command prompt. On the main menu bar, click Kernel, and select Restart and Clear Outputs of All Cells to free up the GPU memory. First, we install the E2B code interpreter SDK and Groq's Python SDK. Model Access. Apr 26, 2024 · Calling Llama 3. Then you will see it immediately and can execute it. LLMs/Chat Models; Embedding Models; Prompts / Prompt Templates Specify the file path of the mount, eg. 2. Build an AI chatbot with both Mistral 7B and Llama2. Computational Notebook documents: A shareable Aug 8, 2023 · 1. Install Jupyter Notebook: Write and enter following text in terminal. This is a great fine-tuning dataset as it teaches the model a unique form of desired output on which the base model performs poorly out-of-the box, so it's helpful to easily and inexpensively gauge whether the fine-tuned model has learned well. 6. Tutorials: Step-by-step guides to help you get started with working on large language models, whether you're a beginner or an experienced practitioner. Contribute to tairov/llama2. Python 3. Launching a Jupyter notebook with "Conda" via UI (Control Panel) Nov 20, 2023 · Load the Llama-2 7b chat model from Hugging Face Hub in the notebook. The LLM model used in this May 29, 2024 · Obtain access from the Hugging Face Llama 3 8b Instruct website. If you require environment management Oct 18, 2023 · There are a few options for getting jupyter notebooks on a Gaudi 2 instance: Connect to the instance remote host using SSH from an IDE like VScode or PyCharm and run Jupyter Lab inside the IDE. In the text box under Registry, specify your Docker ID and a name for the volume. Powered by Llama 2. cpp and Jupyter Lab. %pip install groq e2b_code_interpreter. from_pretrained. a hosted Jupyter notebook environment, isn’t a real prerequisite, we recommend using it to get access to a GPU and Ollama-Companion, developed for enhancing the interaction and management of Ollama and other large language model (LLM) applications, now features Streamlit integration. model └── tokenizer_checklist. Particularly, we're using the Llama2-7B model deployed by the Andreessen Horowitz (a16z) team and hosted on the Replicate platform. The jupyter folder is created at path:- C:\Users\deviv_000\AppData\Roaming\jupyter your name will replace->deviv_000. Get up and running with Llama 3, Mistral, Gemma 2, and other large language models. 00GHz CPU family: 6 Model: 85 Thread(s) per core: 2 Core(s) per socket: 2 Socket(s): 1 Stepping: 3 BogoMIPS: 4000. Short Jupyter Notebook explaining how to use Llama 2 on the Lyra server - GitHub - jaszlo/Llama2OnLyraEdit: Short Jupyter Notebook explaining how to use Llama 2 on the Lyra server Open the starter_kit_notebook. eg. q8_0. org, a free public service provided by the Jupyter community. Contribute to yuyatinnefeld/llama-2 development by creating an account on GitHub. Das geht nur wenn ihr von META die Lizenzbestimmungen angenommen habt und für die Registrierung bei META die gleiche E-Mailadresse verwendet habt die ihr auch bei Hugging Face nutzt. Jul 30, 2023 · For this, we’ll be using Jupyter Notebook. Tok . Aug 4, 2023 · A Jupyter Notebook Chat Assistant built on Llama 2. chk │ ├── consolidated. I have a conda venv installed with cuda and pytorch with cuda support and python 3. So I am ready to go. Installing Jupyter. Projects for using a private LLM (Llama 2) for chat with PDF files, tweets sentiment analysis. Run the fine-tuning notebook: Clone the Llama-recipies repo: git clone LangChain is a framework for developing applications powered by large language models (LLMs). This demonstration shows how to set up a Llama 2 chatbot in about 100 lines of code. AutoModelForCausalLM. Navigate to secure cloud. ipynb; Jupyter Notebook 55 This was posted quite a bit ago, but in case other people are looking for an explanation and solution to the problem of running asynchronous code inside Jupyter Notebook; Jupyter's Tornado 5. Execute scripts in Notebook; step-1. It stands out by not requiring any API key, allowing users to generate responses seamlessly. We will be working in Jupyter notebook. As always in the cloud, keep in mind your use of storage, and billing expectations. By providing it with a prompt, it can generate responses that continue the conversation or expand on the given prompt. Llama 2 is an open source large language model created by Meta AI . 4% We will start by downloading and installing the GPT4ALL on Windows by going to the official download page. You can change the default cache directory of the model weights by adding an cache_dir="custom new directory path/" argument into transformers. I am using Jupyter in VS code. Other instances like 8xA100 with the same amount of VRAM or more should work too. Jul 24, 2023 · 5️⃣ 5 Jupyter Notebook Tricks I Only Discovered 2 Years Into My Data Science Career - Jupyter is a key tool for many Data Scientists and Analysts, yet lots of us only know the basic commands and don’t take advantage of Jupyer’s time-saving tricks, even though they take just 2 minutes to set up. chains. 00. Jupyter Notebook is maintained by the people at Project Jupyter. Variations Llama 2 comes in a range of parameter sizes — 7B, 13B, and 70B — as well as pretrained and fine-tuned variations. After that, select the right framework, variation, and version, and add the model. A jupyter notebook to build and run llama. json; Now I would like to interact with the model. The files a here locally downloaded from meta: folder llama-2-7b-chat with: checklist. You can launch the notebook from the OVHcloud Control Panel or via the ovhai CLI. So in Colab, I can start off with either To allow easy access to Meta Llama models, we are providing them on Hugging Face, where you can download the models in both transformers and native Llama 3 formats. Navigate to the code/llama-2-[XX]b directory of the project. Output Models generate text only. The code includes optional arguments for max_length (controlling the maximum length of the generated text) and num_return_sequences (specifying the number of The Jupyter notebook combines two components: A web application: A browser-based editing program for interactive authoring of computational notebooks which provides a fast interactive environment for prototyping and explaining code, exploring and visualizing data, and sharing ideas with others. A modular design invites extensions Oct 30, 2023 · If you have followed the instructions above correctly, running this sample should be as easy as executing all of the cells in the Jupyter Notebook. ipynb; step-2. 5. Create a PromptTemplate with LangChain and use it to create prompts for your use case. 6 of Llama 2 using !pip install llama-cpp-python . 4 Llama-cpp-python using !CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install --upgrade llama-cpp-python. Its flexible interface allows users to configure and arrange workflows in data science, scientific computing, computational journalism, and machine learning. Copy Model Path. chk. Colab is especially well suited to machine learning, data science, and education. I installed version 0. executable and sys. Setup. Go to the Session options and select the GPU P100 as an accelerator. pth │ └── params. This notebook walks through downloading the Llama 2-7B model from Hugging Face, preparing a custom dataset, and p-tuning the base model against the dataset. 04 sec Question: Why is JupyterGoBoom obsolete? Answer: JupyterGoBoom is considered obsolete because modern software developers have come to realize that Jupyter notebooks become unmaintainable all by themselves. json ├── tokenizer. from_pretrained(. Click File, select the New dropdown, and create a new Notebook. Aug 7, 2023 · Befehl: jupyter notebook. Jul 18, 2023 · A user for AI Notebooks; To access LLaMA 2 models, you will also need to follow the requirements indicated in the notebook. 11. This can only be done with LLaMA 7B. - No data is used for training language m May 5, 2024 · Issues with Downloading Llama2 in Jupyter Notebook. Feb 29. Jupyter Notebook: llama-2-70b-chat-agent. Model Architecture Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. Next to the jupyter-data volume, select the Export volume icon. html Jul 18, 2023 · A user for AI Notebooks; To access LLaMA 2 models, you will also need to follow the requirements indicated in the notebook. ipynb. 80. Before we get started, you will need to install panel==1. Line magics operate on a single line of a code cell. Our fine-tuned LLMs, called Llama 2-Chat, are optimized for dialogue use cases. To download the weights, visit the meta-llama repo containing the model you’d like to use. This page has links to interactive demos that allow you to try some our tools for free online, thanks to mybinder. 🌎; 🚀 Deploy. 2 Jupyter Notebook. A cell is a multiline text input field, and its contents can be executed by using Shift - Enter, or by clicking either the “Play” button the toolbar, or Cell, Run in the menu bar. 1. py file in this repository. LangChain & Prompt Engineering tutorials on Large Language Models (LLMs) such as ChatGPT with custom data. Fine-tune LLaMA 2 (7-70B) on Amazon SageMaker, a complete guide from setup to QLoRA fine-tuning and deployment on Amazon This repository contains a chatbot demonstration built using the Llama 2 model and the LangChain framework, implemented within a Jupyter Notebook. Run open-source LLM, such as Llama 2,mistral locally. JupyterLab is the latest web-based interactive development environment for notebooks, code, and data. This will output a list of the available line magics and cell magics, and it will also tell you whether "automagic" is turned on. Aug 5, 2023 · I would like to use llama 2 7B locally on my win 11 machine with python. Startup jupyter by running jupyter lab in a terminal or command prompt Update the auth_token variable in the notebook. SSH Tunnel into the instance from your local machine and open Jupyter Lab directly in your local browser. Hit the ground running using third-party integrations and Templates. Mar 7, 2023 · You can run LLaMA 7B with single GPU by referring to the above code. In this repository, you will find a variety of prompts that can be used with Llama. Blog. Command: jupyter Aug 24, 2023 · Navigate to the AWS DLC repository. 8w次，点赞166次，收藏299次。Jupyter notebook 中使用pip install本文参照stack overflow修改而来Markdown和扩展Markdown简洁的语法代码块高亮图片链接和图片上传LaTex数学公式UML序列图和流程图离线写博客导入导出Markdown文件丰富的快捷键快捷键加粗 Ctrl + B 斜体 Ctrl + I 引用 Ct_在jupyter中使用pip Llama 3. Denkt daran wenn ihr das Jupyter Notebook ausführt das ihr ein Hugging Face token braucht um das Llama 2 Modell herunter laden zu können. 5. Open the Volumes Backup & Share extension in the Docker Dashboard. Jul 18, 2023 · Llama 2 is a family of state-of-the-art open-access large language models released by Meta today, and we’re excited to fully support the launch with comprehensive integration in Hugging Face. Refer to the Hugging Face Hub for a listing of available Llama3 models and their access requirements. This app was refactored from a16z's implementation of their LLaMA2 Chatbot to be light-weight for deployment to the Streamlit Community Cloud. Open the notebook llama2-7b-fine-tuning. Here are the initial setup steps: from dotenv import load_dotenv, This page of TheBloke/Llama-2–7B-Chat-GGML is somewhat easier to follow The Jupyter Notebook is an open source web application that you can use to create and share documents that contain live code, equations, visualizations, and text. Try Jupyter. 3. - No data goes to OpenAI. Downloading groq-0. demo. Setting up AWS SageMaker. This now gives us a Hugging Face model that we can fine-tune leveraging Huggingface libraries! 3. Is Llama-2 right for me? Llama-2 is a very powerful model for building your own generative text and chat applications, it comes with a very competitive performance and a permissive license for research and We can click on it, and a jupyter environment opens in our local browser. Aug 18, 2023 · Install, run and chat with Llama 2 on your Mac or Windows laptop, using llama. LangChain simplifies every stage of the LLM application lifecycle: Development: Build your applications using LangChain's open-source building blocks and components. We’ll be using it shortly. Llama 2 is being released with a very permissive community license and is available for commercial use. Fine-tuning is often used as a means to update a model for a specific task or tasks to better respond to domain-specific prompts. I’ve recently been having some problems loading up some Llama2 models on HuggingFace through a Jupyter Notebook. 0 update bricked asyncio functionalities after the addition of its own asyncio event loop: Thus, for any asyncio functionality to run on Jupyter Notebook Aug 9, 2023 · Here are the steps to create a RunPod. Launching a Jupyter notebook with "Conda" via UI (Control Panel) 文章浏览阅读9. View Notebook: llama2-qa. Connecting Llama 3 and code interpreter. py development by creating an account on GitHub. We start with a foundational Llama-2–7B-hf from Hugging Face and fine-tune it on the openassistant-guanaco dataset for causal language modeling text generation. Jul 30, 2023 · Jupyter Notebook. lg zq th lz gs kc qr ys cj iy